{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6470933556556702, "min": 0.5685675740242004, "max": 1.507969617843628, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19236.791015625, "min": 16984.25, "max": 45745.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989910.0, "min": 29952.0, "max": 989910.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989910.0, "min": 29952.0, "max": 989910.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2979535162448883, "min": -0.16834713518619537, "max": 0.2979535162448883, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 76.57405090332031, "min": -39.89826965332031, "max": 76.57405090332031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.025349557399749756, "min": -0.025349557399749756, "max": 0.25741860270500183, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.514836311340332, "min": -6.514836311340332, "max": 61.78046417236328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07188226819990258, "min": 0.06446526338164833, "max": 0.07341709901906122, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.006351754798636, "min": 0.5062338405368373, "max": 1.0471331936241055, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012349764262318317, "min": 4.5875234415147196e-05, "max": 0.012349764262318317, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17289669967245644, "min": 0.0006422532818120607, "max": 0.17289669967245644, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.517904636921427e-06, "min": 7.517904636921427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010525066491689998, "min": 0.00010525066491689998, "max": 0.0032538437153854993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025059357142857, "min": 0.1025059357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350831, "min": 1.3691136000000002, "max": 2.4003799000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002603429778571428, "min": 0.0002603429778571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036448016899999994, "min": 0.0036448016899999994, "max": 0.10848298855, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011332578957080841, "min": 0.011332578957080841, "max": 0.42844635248184204, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15865610539913177, "min": 0.15865610539913177, "max": 2.999124526977539, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 565.25, "min": 552.7636363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31654.0, "min": 15984.0, "max": 32727.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1379017878662456, "min": -1.0000000521540642, "max": 1.1379017878662456, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 62.58459833264351, "min": -32.000001668930054, "max": 62.58459833264351, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1379017878662456, "min": -1.0000000521540642, "max": 1.1379017878662456, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 62.58459833264351, "min": -32.000001668930054, "max": 62.58459833264351, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06665856012735855, "min": 0.06665856012735855, "max": 8.341605023480952, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.66622080700472, "min": 3.524839514604537, "max": 133.46568037569523, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686600770", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686602789" }, "total": 2019.2556495639997, "count": 1, "self": 0.4744284409998727, "children": { "run_training.setup": { "total": 0.03717722200008211, "count": 1, "self": 0.03717722200008211 }, "TrainerController.start_learning": { "total": 2018.7440439009997, "count": 1, "self": 1.2269298569117382, "children": { "TrainerController._reset_env": { "total": 5.353851383999881, "count": 1, "self": 5.353851383999881 }, "TrainerController.advance": { "total": 2012.0727420220887, "count": 63347, "self": 1.296532454025055, "children": { "env_step": { "total": 1396.8224617259589, "count": 63347, "self": 1293.7689100669077, "children": { "SubprocessEnvManager._take_step": { "total": 102.32463929802088, "count": 63347, "self": 4.5050548930967125, "children": { "TorchPolicy.evaluate": { "total": 97.81958440492417, "count": 62545, "self": 97.81958440492417 } } }, "workers": { "total": 0.728912361030325, "count": 63347, "self": 0.0, "children": { "worker_root": { "total": 2014.6325147479033, "count": 63347, "is_parallel": true, "self": 824.8980773329586, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025093300000662566, "count": 1, "is_parallel": true, "self": 0.0007020000002739835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018073299997922732, "count": 8, "is_parallel": true, "self": 0.0018073299997922732 } } }, "UnityEnvironment.step": { "total": 0.0628960859999097, "count": 1, "is_parallel": true, "self": 0.0005667399996127642, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005437660001916811, "count": 1, "is_parallel": true, "self": 0.0005437660001916811 }, "communicator.exchange": { "total": 0.05997727900012251, "count": 1, "is_parallel": true, "self": 0.05997727900012251 }, "steps_from_proto": { "total": 0.0018083009999827482, "count": 1, "is_parallel": true, "self": 0.00034545700009402935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014628439998887188, "count": 8, "is_parallel": true, "self": 0.0014628439998887188 } } } } } } }, "UnityEnvironment.step": { "total": 1189.7344374149448, "count": 63346, "is_parallel": true, "self": 31.702082403872282, "children": { "UnityEnvironment._generate_step_input": { "total": 21.925279990086437, "count": 63346, "is_parallel": true, "self": 21.925279990086437 }, "communicator.exchange": { "total": 1040.5873098739567, "count": 63346, "is_parallel": true, "self": 1040.5873098739567 }, "steps_from_proto": { "total": 95.51976514702937, "count": 63346, "is_parallel": true, "self": 18.343360087977544, "children": { "_process_rank_one_or_two_observation": { "total": 77.17640505905183, "count": 506768, "is_parallel": true, "self": 77.17640505905183 } } } } } } } } } } }, "trainer_advance": { "total": 613.9537478421048, "count": 63347, "self": 2.2691725380814205, "children": { "process_trajectory": { "total": 101.6078569140218, "count": 63347, "self": 101.40587221002215, "children": { "RLTrainer._checkpoint": { "total": 0.20198470399964208, "count": 2, "self": 0.20198470399964208 } } }, "_update_policy": { "total": 510.0767183900016, "count": 438, "self": 325.00647013302796, "children": { "TorchPPOOptimizer.update": { "total": 185.07024825697363, "count": 22884, "self": 185.07024825697363 } } } } } } }, "trainer_threads": { "total": 8.319993867189623e-07, "count": 1, "self": 8.319993867189623e-07 }, "TrainerController._save_models": { "total": 0.09051980599997478, "count": 1, "self": 0.001350204999653215, "children": { "RLTrainer._checkpoint": { "total": 0.08916960100032156, "count": 1, "self": 0.08916960100032156 } } } } } } }